README.md

---
license: apache-2.0
base_model: openbmb/MiniCPM5-1B
library_name: transformers
pipeline_tag: text-generation
tags:
- minicpm
- minicpm5
- minicpm5-1b
- tool-calling
- function-calling
- tool-use
- agentic
- xml-tool-calling
- transformers
- sglang
- vllm
- safetensors
- merged-model
- nemotron
- dpo
- openbmb
widget:
- text: "Use the available tool to create a note titled Team Meeting Agenda."
- text: "Run tests for the calculator bug using the available tool."
datasets:
- Team-ACE/ToolACE
model-index:
- name: MiniCPM5-1B-Agentic-Tooluse-v2
  results:
  - task:
      type: text-generation
      name: Tool calling
    dataset:
      name: External ToolACE-derived first-call evaluation (held-out 300 examples)
      type: Team-ACE/ToolACE
    metrics:
    - type: parseable_rate
      value: 0.9933
      name: Parseable tool-call rate
    - type: valid_name_rate
      value: 0.9700
      name: Valid available-tool name rate
    - type: expected_name_rate
      value: 0.9267
      name: Expected tool-name rate
    - type: args_exact_rate
      value: 0.6533
      name: Exact-arguments rate
    - type: arg_key_overlap
      value: 0.7517
      name: Argument-key overlap
    - type: no_schema_copy_rate
      value: 1.0000
      name: No-schema-copy rate
    - type: no_repetition_rate
      value: 1.0000
      name: No-repetition rate
    - type: stopped_cleanly_rate
      value: 0.1500
      name: Stopped-cleanly rate
---

# MiniCPM5-1B Agentic Tooluse Merged FP16

Standalone merged FP16 checkpoint of
[`openbmb/MiniCPM5-1B`](https://huggingface.co/openbmb/MiniCPM5-1B)
and the latest
[`MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2`](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2)
adapter after the July 2026 Nemotron SFT+DPO repair.

This repository contains the complete model. It is **not** an adapter and does not require PEFT at inference time.

## Base model architecture

MiniCPM5-1B uses a standard `LlamaForCausalLM` architecture:

| Property | Value |
|---|---|
| Parameters (total) | 1,080,632,832 |
| Parameters (non-embedding) | 679,552,512 |
| Architecture | `LlamaForCausalLM` |
| Layers | 24 |
| Attention heads (GQA) | 16 Q / 2 KV |
| Context length | 131,072 tokens |
| Training | SFT → RL (GRPO) fine-tune on [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) |

## Thinking mode

MiniCPM5-1B has a built-in `<think>...</think>` chat template. The same checkpoint can act as a fast assistant **or** a deliberate chain-of-thought reasoner — controlled by a single flag:

```python
# Fast mode — recommended for tool calling (thinking OFF)
prompt = tokenizer.apply_chat_template(
    messages, tools=tools, add_generation_prompt=True,
    enable_thinking=False,
    tokenize=False,
)

# Reasoning mode (thinking ON — NOT recommended for tool calling)
prompt = tokenizer.apply_chat_template(
    messages, tools=tools, add_generation_prompt=True,
    enable_thinking=True,
    tokenize=False,
)
```

> **Important:** always use `enable_thinking=False` for tool/function calling. With thinking ON the model spends its token budget inside `<think>...</think>` and may not reach a completed function call. All benchmark numbers in this card use thinking OFF.

## Citation

If you use this model, please cite the base model paper:

```bibtex
@article{minicpm4,
  title   = {MiniCPM4: Ultra-Efficient LLMs on End Devices},
  author  = {MiniCPM Team},
  journal = {arXiv preprint arXiv:2506.07900},
  year    = {2025}
}
```

And the ToolACE dataset used for fine-tuning:

```bibtex
@article{toolace,
  title   = {ToolACE: Winning the Points of LLM Function Calling},
  author  = {Liu, Ying and others},
  journal = {arXiv preprint arXiv:2409.00920},
  year    = {2024}
}
```

## ModelScope

The base model is also available on ModelScope (for users in China and East Asia):

- [OpenBMB/MiniCPM5-1B on ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B)

*(The fine-tuned adapter/GGUF builds are currently HuggingFace-only.)*
## Related repos

### Latest v3 release

| Format | Repository |
|--------|-----------|
| LoRA adapter (PEFT, smallest download, fine-tune further) | [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3) |
| Merged full-weight FP16 (transformers / vLLM / SGLang serving) | [MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16) |
| GGUF quantizations (llama.cpp / Ollama / LM Studio, CPU-friendly) | [MiniCPM5-1B-Agentic-Tooluse-v3-GGUF](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF) |

### v2 family (this release)

| Format | Repository |
|--------|-----------|
| v2 LoRA adapter | [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2) |
| v2 Merged FP16 | [MiniCPM5-1B-Agentic-Tooluse-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16) |
| v2 GGUF | [MiniCPM5-1B-Agentic-Tooluse-GGUF](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-GGUF) |
## Current Files

The current model weights are one indexed checkpoint:

- `model-00001-of-00002.safetensors`
- `model-00002-of-00002.safetensors`
- `model.safetensors.index.json`

The repository also includes the matching tokenizer, `chat_template.jinja`, model configuration, generation configuration and external evaluation artifacts. The previous single-file model remains recoverable from Hub history but is not part of the current branch.

## Tool-Calling Behavior

MiniCPM5-1B natively emits XML-style calls:

```xml
<function name="tool_name"><param name="parameter">value</param></function>
```

The fine-tuning specializes first-call tool selection, function-name accuracy, argument selection, schema-copy avoidance and repeated-call suppression.

An application remains responsible for parsing and validating calls, executing tools externally, and returning tool results in a new turn.

## Recommended Tool-Calling Deployment

OpenBMB recommends SGLang with its built-in MiniCPM5 parser:

```bash
pip install "sglang[srt]>=0.5.12"

python -m sglang.launch_server \
  --model-path ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16 \
  --port 30000 \
  --tool-call-parser minicpm5
```

The parser converts a completed `<function ...>...</function>` block into an OpenAI-compatible `tool_calls` response.

## Transformers

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.float16,
    device_map="auto",
)
model.eval()
```

Use `tokenizer.apply_chat_template(...)` and the repository's matching chat template. For deterministic tool selection, override the sampling defaults:

```python
outputs = model.generate(
    **inputs,
    do_sample=False,
    max_new_tokens=128,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
)
```

Remove `token_type_ids` from `inputs` if the installed Transformers/tokenizer combination returns them, because this Llama model does not consume that argument.

## vLLM

The merged safetensors checkpoint is the preferred format for vLLM:

```bash
vllm serve ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16
```

Parser availability depends on the installed vLLM release. Use SGLang's official `minicpm5` parser path when OpenAI-compatible tool-call extraction is required and the vLLM build does not provide an equivalent parser.

## External Evaluation

The final adapter and this merged checkpoint have identical weights for evaluation purposes. Evaluation used 300 examples derived from the external
[`Team-ACE/ToolACE`](https://huggingface.co/datasets/Team-ACE/ToolACE)
dataset, deterministic decoding, and the same cases for both models. This is not an official ToolACE or BFCL leaderboard submission.

| Metric | Base MiniCPM5-1B | Repaired model | Delta |
|---|---:|---:|---:|
| Parseable tool call | 0.0133 | 0.9933 | +0.9800 |
| Valid available-tool name | 0.0133 | 0.9700 | +0.9567 |
| Expected tool name | 0.0133 | 0.9267 | +0.9133 |
| Exact arguments | 0.1500 | 0.6533 | +0.5033 |
| Argument-key overlap | 0.0033 | 0.7517 | +0.7484 |
| No schema copying | 1.0000 | 1.0000 | +0.0000 |
| No repetition | 0.9967 | 1.0000 | +0.0033 |
| Natural clean termination | 0.0000 | 0.1500 | +0.1500 |

The full rows and metrics are published in:

- `external_toolace_base_vs_nemotron_dpo_eval.json`
- `EVAL_RESULTS.md`

## Understanding the 15% Termination Metric

`stopped_cleanly_rate=0.15` is a strict natural-termination metric. It measures whether the model naturally ended immediately after a completed function call without runtime intervention.

It does **not** mean that only 15% of cases produced usable calls. In the same evaluation, 99.33% were parseable, 97% used an available tool name, and 92.67% selected the expected tool.

MiniCPM5's deployment contract uses a parser to extract the completed XML function block. Production should treat the first completed `</function>` as the action boundary and prevent generated synthetic tool responses or later dialogue from being interpreted as additional actions.

## Training Lineage

The current adapter was produced by:

1. Earlier xLAM/Glaive SFT and preference-repair stages.
2. Targeted Nemotron SFT continuation from the previous DPO adapter.
3. DPO preference optimization over valid versus corrupted tool calls.
4. Merge into `openbmb/MiniCPM5-1B`.

Nemotron sources used in the repair:

- `nvidia/Nemotron-SFT-Agentic-v2`
- `nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1`
- `nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1`

The data pipeline inspected physical dataset files, skipped one malformed JSONL row in the SFT tool-calling file, removed oversized policy text where needed, preserved tool schemas and recent context, and rejected unknown arguments, schema-copy placeholders and invalid expected tools.

## Measured Improvements and Scope

This merged checkpoint contains the same repaired adapter behavior and improved every reported task-quality metric over base MiniCPM5-1B:

- Parseable calls: **1.33% -> 99.33%**
- Valid available-tool names: **1.33% -> 97.00%**
- Expected-tool selection: **1.33% -> 92.67%**
- Exact arguments: **15.00% -> 65.33%**
- Argument-key overlap: **0.33% -> 75.17%**
- No repetition: **99.67% -> 100.00%**
- Natural clean termination: **0.00% -> 15.00%**

The remaining gap to 100% is residual error after a large improvement, not evidence that merging or fine-tuning degraded the base model.

## Deployment Notes

- Schema validation, permission checks and confirmation for sensitive actions are standard requirements for every tool-calling model.
- Exact-argument accuracy improved by **50.33 percentage points**; applications should still validate generated values before execution.
- Valid-name accuracy improved by **95.67 percentage points**; rare near misses can remain on unseen tool libraries.
- Natural termination improved from 0% to 15%. MiniCPM5's parser-based serving contract extracts the completed call, so this metric is separate from the 99.33% parseable-call rate.
- The external evaluation is custom rather than an official ToolACE/BFCL leaderboard submission.
- GGUF quantizations may differ slightly from FP16 and are published separately.

## Limitations